Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Tx1207/hello-scholar --skill ponytailgit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tx1207/hello-scholar/ponytail)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/ponytail"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/ponytail/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tx1207/hello-scholar/ponytail"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/ponytail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.00796 |
| Opus 5.5 | $0.00023 | $0.00318 |
| Sonnet 5.5 | $0.00011 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
ponytail scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ponytail
Reduce the effort needed to understand and change the code by keeping the mechanisms the current problem actually needs. Work from behavior and responsibility, not a deletion target. A successful cleanup leaves a smaller, coherent implementation with the required contracts still intact.
Identify the necessary complexity
Use the scope named by the user or already established for the current change. Read the target and its relevant callers, tests, configuration, and contracts before selecting a simplification. If the scope is unresolved and the plausible choices would change the work materially, clarify it. Do not turn a bounded cleanup into a repository-wide refactor.
For each candidate mechanism, ask what current outcome it protects and what would happen if it were removed, merged, or replaced by an existing capability. Trace that answer to actual use:
- An indirection with no separate responsibility may disappear into its caller. A real boundary with independent policy or lifecycle may need to remain.
- Similar implementations may be merged when they express the same rule and must change together. Preserve separate implementations when their contracts or reasons to change differ; visual similarity is not evidence of one responsibility.
- An option with no current use may be removable, but a public configuration or persisted format has consumers beyond a local text search. Confirm that contract before changing it.
- A guard can be redundant when an earlier boundary establishes the invariant for every caller. Keep it when it handles a reachable failure or protects a trust boundary.
Prefer removing mechanisms with no required outcome, then reusing a suitable project capability, standard-library facility, or installed dependency. Choose the minimum new implementation only when those options do not satisfy the contract. An opaque one-liner or a new general-purpose abstraction can increase reading effort despite reducing the diff.
Explain the concrete simplification and why it preserves what matters. For already authorized cleanup, continue directly to the change. When the request asks only whether something is overengineered or asks for a proposal, return the assessment without edits.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 40 lines · 57 tokens per session scan A 8836cb38d4a7
ponytail is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 796 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-21.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…